Fault Detection and Localization in Motorcycles Based on the Chain Code of Pseudospectra and Acoustic Signals

B.S. Anami; V.B. Pagi

doi:10.15282/jmes.4.2013.7.0041

Authors

B.S. Anami KLE Institute of Technology, Opp. Airport, Gokul, Hubli – 580 030, India
V.B. Pagi Faculty of Computer Applications, Basaveshwar Engineering College S. Nijalingappa Vidyanagar, Bagalkot – 587102, India

DOI:

https://doi.org/10.15282/jmes.4.2013.7.0041

Keywords:

Motorcycle fault diagnosis; pseudospectral analysis; acoustic signal; DTW classifier.

Abstract

Vehicles produce sound signals with varying temporal and spectral properties under different working conditions. These sounds are indicative of the condition of the engine. Fault diagnosis is a significantly difficult task in geographically remote places where expertise is scarce. Automated fault diagnosis can assist riders to assess the health condition of their vehicles. This paper presents a method for fault detection and location in motorcycles based on the chain code of the pseudospectra and Mel-frequency cepstral coefficient (MFCC) features of acoustic signals. The work comprises two stages: fault detection and fault location. The fault detection stage uses the chain code of the pseudospectrum as a feature vector. If the motorcycle is identified as faulty, the MFCCs of the same sample are computed and used as features for fault location. Both stages employ dynamic time warping for the classification of faults. Five types of faults in motorcycles are considered in this work. Observed classification rates are over 90% for the fault detection stage and over 94% for the fault location stage. The work identifies other interesting applications in the development of acoustic fingerprints for fault diagnosis of machinery, tuning of musical instruments, medical diagnosis, etc.

References

Anami, B. S., Pagi, V. B., & Magi, S. M. (2011). Wavelet based acoustic analysis for determining health condition of motorized two-wheelers. Journal of Applied Acoustics, 72(7), 464-469.

Engin, S. N., & Gulez, K. A. (1999). Wavelet transform–artificial neural networks (WT-ANN) based rotating machinery fault diagnostics methodology. IEEE NSIP’ 99, Falez Hotel, Antalya, Turkey, pp. 714-720.

He, D., Li, R., & Bechhoefer, E. (2010). Split torque type gearbox fault detection using acoustic emission and vibration sensors. IEEE International Conference on Networking, Sensing and Control (ICNSC), pp. 62-66.

Heidarbeigi, K., Ahmadi, H., Omid, M., & Tabatabaeefar, A. (2009). Fault diagnosis of Massey Ferguson gearbox using power spectral density. Journal of Agricultural Technology, 5(1), 1-6.

IR (India-Reports on February 20). (2010). Retrieved from http://india-reports.in/future-growth-global-transitions/economy-in-transition/two-wheeler-segment-in-india/ (Accessed on 12-09-2010).

JunHong, Z., & Bing, H. (2005). Analysis of engine front noise using sound intensity techniques. Journal of Mechanical Systems and Signal Processing, 19, 213-221.

Lin, J., & Zuo, M. J. (2003). Gearbox fault diagnosis using adaptive wavelet filter, Journal of Mechanical Systems and Signal Processing, 17(6), 1259-1269.

MFCC (Mel-Frequency Cepstral Coefficients). (2012). Retrieved from http://en.wikipedia.org/wiki/Mel-frequency_cepstrum.

Paulraj, M. P, Yaacob, S., & Mohd Zubir, M. Z. (2009). Motorbike engine faults diagnosing system using entropy and functional link neural network in wavelet domain. Proc. of the Int. Conf. on Man-Machine Systems (ICoMMS) 11–13 October 2009, Batu Ferringhi, Penang, MALAYSIA, pp. 2B4-1-2B4-5.

PMUSIC function of MATLAB, http://www.mathworks.in/help/toolbox/signal/ pmusic.html, (Accessed on 10-11-2012).

Sakoe, H., & Chiba, S. (1978). Dynamic programming algorithm optimization for spoken word recognition. IEEE Transactions on Acoustics, Speech and Signal Processing, 26(1): 43-49.

Tan, C. L., & Wong, S. V. (2012). Motorcycle crash test center: a movable barrier approach. International Journal of Automotive and Mechanical Engineering, 5, 630-638.

Wu, J. D., Chang, E. C., Liao, S. Y., Kuo, J. M., & Huang, C. K. (2009). Fault classification of a scooter engine platform using wavelet transform and artificial neural network. Proc. of the International Multi Conference of Engineers and Computer Scientists, IMECS 2009, March 18–20, 2009, Hong Kong, 1, 58-63.